Push model using huggingface_hub.
Browse files- README.md +26 -36
- config_setfit.json +2 -2
README.md
CHANGED
@@ -12,19 +12,18 @@ metrics:
|
|
12 |
- recall
|
13 |
- f1
|
14 |
widget:
|
15 |
-
- text:
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
- text:
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
, terima kasih , pak .
|
28 |
pipeline_tag: text-classification
|
29 |
inference: true
|
30 |
model-index:
|
@@ -39,30 +38,21 @@ model-index:
|
|
39 |
split: test
|
40 |
metrics:
|
41 |
- type: accuracy
|
42 |
-
value: 0.
|
43 |
name: Accuracy
|
44 |
- type: precision
|
45 |
-
value: 0.
|
46 |
name: Precision
|
47 |
- type: recall
|
48 |
-
value: 0.
|
49 |
name: Recall
|
50 |
- type: f1
|
51 |
-
value: 0.
|
52 |
name: F1
|
53 |
---
|
54 |
|
55 |
# SetFit with firqaaa/indo-sentence-bert-base
|
56 |
|
57 |
-
## Author
|
58 |
-
|
59 |
-
**Kelompok 3 :**
|
60 |
-
|
61 |
-
- Muhammad Guntur Arfianto (20/459272/PA/19933)
|
62 |
-
- Putri Iqlima Miftahuddini (23/531392/NUGM/01467)
|
63 |
-
- Alan Kurniawan (23/531301/NUGM/01382)
|
64 |
-
|
65 |
-
|
66 |
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
67 |
|
68 |
The model has been trained using an efficient few-shot learning technique that involves:
|
@@ -98,9 +88,9 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
98 |
## Evaluation
|
99 |
|
100 |
### Metrics
|
101 |
-
| Label | Accuracy | Precision | Recall | F1
|
102 |
-
|
103 |
-
| **all** | 0.
|
104 |
|
105 |
## Uses
|
106 |
|
@@ -120,7 +110,7 @@ from setfit import SetFitModel
|
|
120 |
# Download from the 🤗 Hub
|
121 |
model = SetFitModel.from_pretrained("TRUEnder/setfit-indosentencebert-indonlusmsa-8-shot")
|
122 |
# Run inference
|
123 |
-
preds = model("
|
124 |
```
|
125 |
|
126 |
<!--
|
@@ -180,12 +170,12 @@ preds = model("menang di 3 pilgub pulau jawa , ppp optimis dilirik jadi cawapres
|
|
180 |
### Training Results
|
181 |
| Epoch | Step | Training Loss | Validation Loss |
|
182 |
|:-------:|:------:|:-------------:|:---------------:|
|
183 |
-
| 1.0 | 24 | 0.0498 | 0.
|
184 |
-
| 2.0 | 48 | 0.0032 | 0.
|
185 |
-
| 3.0 | 72 | 0.0014 | 0.
|
186 |
-
| **4.0** | **96** | **0.001** | **0.
|
187 |
-
| 5.0 | 120 | 0.0009 | 0.
|
188 |
-
| 6.0 | 144 | 0.0008 | 0.
|
189 |
|
190 |
* The bold row denotes the saved checkpoint.
|
191 |
### Framework Versions
|
|
|
12 |
- recall
|
13 |
- f1
|
14 |
widget:
|
15 |
+
- text: halaman 97 - 128 tidak ada , diulang halaman 65 - 96 , pembelian hari minggu
|
16 |
+
tanggal 24 desember sore sekitar jam 4 pembayaran menggunakan kartu atm bri bersamaan
|
17 |
+
dengan buku the puppeteer dan sirkus pohon
|
18 |
+
- text: liverpool sukses di kandang tottenham
|
19 |
+
- text: hai angga , untuk penerbitan tiket reschedule diharuskan melakukan pembayaran
|
20 |
+
dulu ya .
|
21 |
+
- text: sedih kalau umat diprovokasi supaya saling membenci .
|
22 |
+
- text: berada di lokasi strategis jalan merdeka , berseberangan agak ke samping bandung
|
23 |
+
indah plaza , tapat sebelah kanan jalan sebelum traffic light , parkir mobil cukup
|
24 |
+
luas . saus bumbu dan lain-lain disediakan cukup lengkap di lantai bawah . di
|
25 |
+
lantai atas suasana agak sepi . bakso cukup enak dan terjangkau harga nya tetapi
|
26 |
+
kuah relatif kurang dan porsi tidak terlalu besar
|
|
|
27 |
pipeline_tag: text-classification
|
28 |
inference: true
|
29 |
model-index:
|
|
|
38 |
split: test
|
39 |
metrics:
|
40 |
- type: accuracy
|
41 |
+
value: 0.7171717171717171
|
42 |
name: Accuracy
|
43 |
- type: precision
|
44 |
+
value: 0.7171717171717171
|
45 |
name: Precision
|
46 |
- type: recall
|
47 |
+
value: 0.7171717171717171
|
48 |
name: Recall
|
49 |
- type: f1
|
50 |
+
value: 0.7171717171717171
|
51 |
name: F1
|
52 |
---
|
53 |
|
54 |
# SetFit with firqaaa/indo-sentence-bert-base
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [firqaaa/indo-sentence-bert-base](https://huggingface.co/firqaaa/indo-sentence-bert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
57 |
|
58 |
The model has been trained using an efficient few-shot learning technique that involves:
|
|
|
88 |
## Evaluation
|
89 |
|
90 |
### Metrics
|
91 |
+
| Label | Accuracy | Precision | Recall | F1 |
|
92 |
+
|:--------|:---------|:----------|:-------|:-------|
|
93 |
+
| **all** | 0.7172 | 0.7172 | 0.7172 | 0.7172 |
|
94 |
|
95 |
## Uses
|
96 |
|
|
|
110 |
# Download from the 🤗 Hub
|
111 |
model = SetFitModel.from_pretrained("TRUEnder/setfit-indosentencebert-indonlusmsa-8-shot")
|
112 |
# Run inference
|
113 |
+
preds = model("liverpool sukses di kandang tottenham")
|
114 |
```
|
115 |
|
116 |
<!--
|
|
|
170 |
### Training Results
|
171 |
| Epoch | Step | Training Loss | Validation Loss |
|
172 |
|:-------:|:------:|:-------------:|:---------------:|
|
173 |
+
| 1.0 | 24 | 0.0498 | 0.2293 |
|
174 |
+
| 2.0 | 48 | 0.0032 | 0.2033 |
|
175 |
+
| 3.0 | 72 | 0.0014 | 0.2021 |
|
176 |
+
| **4.0** | **96** | **0.001** | **0.2009** |
|
177 |
+
| 5.0 | 120 | 0.0009 | 0.2016 |
|
178 |
+
| 6.0 | 144 | 0.0008 | 0.2016 |
|
179 |
|
180 |
* The bold row denotes the saved checkpoint.
|
181 |
### Framework Versions
|
config_setfit.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"normalize_embeddings": false,
|
3 |
+
"labels": null
|
4 |
}
|